139results about "Details involving 3D image data" patented technology

Systems and methods for performing a medical imaging analysis task using a foundation model are provided. One or more 3D (three-dimensional) medical images each comprising a plurality of 2D (two-dimensional) slices are received. A first set of features is extracted from the plurality of 2D slices of the one or more 3D medical images using a machine learning based encoding network. Each respective feature of the first set of features is resampled based on a spatial location of one or more pixels of the 2D slices from which the respective feature was extracted. The resampled first set of features is encoded into a second set of features. A medical imaging analysis task is performed based on the second set of features. Results of the medical imaging analysis task are output.

The application belongs to the field of medical image registration, and particularly relates to a method for constructing a multi-modal three-dimensional medical image segmentation and registration model and application thereof, which comprises the following steps: collecting two kinds of modal medical images of each target as a reference image and a floating image respectively to obtain a training sample; simultaneously optimizing three network parameters by using the training sample to obtain a segmentation and registration model composed of a reference image segmentation model, a floating image segmentation model and a registration model; the reference image and the floating image segmentation model are respectively used for multi-scale segmentation of the corresponding images to obtain multi-scale segmentation results of the maximum scale same as the original images; the registration model is used for obtaining a multi-scale deformation field based on the reference image, the floating image, the maximum scale reference image segmentation result and the floating image segmentation result; and the segmentation loss and the registration loss are all the sum of the segmentation and registration losses at each scale, and the segmentation loss comprises a first gradient loss and / or a level set energy function loss.

Provided is an image processing method. The method includes obtaining an input image, obtaining a sampling grid in which offset information is assigned to a predefined pixel grid, and applying the sampling grid to the input image to reconstruct pixels of the input image to generate a reconstructed image, wherein the offset information may include reconstruction location information for each pixel of the predefined pixel grid.

A measurement device includes a processor. The processor acquires three-dimensional data including three-dimensional coordinates of two or more points on a subject and sets a measurement reference. The processor detects one or more feature regions on the subject and outputs an image of a three-dimensional shape of the subject to a display. The processor selects at least one feature region of the one or more feature regions as a measurement target region. The processor generates distance information indicating a distance between the measurement reference and the measurement point, superimposes a measurement result generated based on the distance information on an image of the measurement target region, and outputs the image on which the measurement result is superimposed to the display.

A computing system receives a first image of a three-dimensional object in a human body. The first image of the three-dimensional object includes a structure located in the three-dimensional object. The computing system receives an indication of a location of the structure in the first image. The computing system defines a main axis of the structure based on the indication of the location of the structure and an orientation of the structure. the computing system determines a two-dimensional plane along the main axis of the structure. The computing system generates a second image of the three-dimensional object and the structure along the two-dimensional plane.

Systems and methods are herein provided for annotation and segmentation of 3D multi-volume imaging data. In one example, a method comprises obtaining three-dimensional (3D) multi-volume imaging data, the 3D multi-volume imaging data comprising a plurality of registered image volumes; determining one or more positions of a user cursor within a first image of a first image volume of the plurality of registered image volumes; determining a contour point position corresponding to each of the one or more positions of the user cursor for two or more of the plurality of registered image volumes; generating two or more segmentation contours corresponding to the two or more of the plurality of registered image volumes; determining, via user input, a selected segmentation contour of the two or more segmentation contours; generating a 3D segmentation mask based at least in part on the selected segmentation contour and saving the 3D segmentation mask to memory.

The application discloses a kind of indoor space three-dimensional color point cloud generation method, utilize the three-dimensional laser SLAM and panoramic video data of indoor collection to generate indoor scene three-dimensional color point cloud, realization process includes indoor space handheld SLAM system data acquisition, indoor space three-dimensional point cloud generation, panoramic position and posture synchronous generation, single frame panoramic and three-dimensional point cloud registration, generate color point cloud.The application is aimed at the generation process of indoor space three-dimensional color point cloud, generates indoor scene point cloud by laser SLAM, and utilizes the pose information of SLAM trajectory to carry out point cloud and panoramic image registration parameter calculation, realizes indoor scene point cloud automatic coloring.This mode solves the problem of lacking initial image pose in point cloud and panoramic image fusion, reduces calculation data volume, improves registration efficiency, provides a new scheme for generating indoor space three-dimensional color point cloud in optoelectronic surveying and mapping field.

A method for displaying a color three-dimensional map, includes: acquiring initial color three-dimensional map information of a space where a robot is located, where the space where the robot is located represents a space corresponding to a region detectable by a robot sensor; completing the color three-dimensional map based on the initial color three-dimensional map information to perform inference-based completion on structural and color information of a region undetected by the robot sensor; and displaying the completed color three-dimensional map obtained after the completing.

The present invention relates to a device (1) and method for generating a geometrical model (33) and a 3D biomechanical model (31) of a spine of a patient and assisting a user in planning a spine treatment for said patient's spine. The present invention further relates to a surrogate model. The 3D biomechanical model (31) and the surrogate model may be configured to generate biomechanical performance indicators and clinical indicators.

Surgical planning based on a three-dimensional (3D) model includes obtaining a 3D model of an anatomical region, wherein the anatomical region includes the patient's anatomical features; identifying at least one deformity, wherein the at least one deformity is identified with respect to a target anatomical value of the patient's anatomical features, wherein the target anatomical value includes a desired range into which the anatomical measurement should fall; and using the anatomical measurement, determining at least one planar correction to be made to at least one anatomical structure of the patient. Generating a 3D model using two-dimensional (2D) imaging data may include performing anatomical context processing, which includes annotating the model, contours, edges, or surfaces of the anatomical structure, as well as performing 2D-to-3D reconstruction to optimize the orientation, placement, and scale of the 3D digital volume modeling the anatomical structure, resulting in a 3D anatomical representation of the anatomical region as a 3D model.

The application relates to a three-dimensional pressure / temperature field reconstruction method based on contour feature matching, which comprises the following steps: S1, obtaining three-dimensional data of a model; S2, obtaining a two-dimensional pressure / temperature cloud chart of the model surface by using pressure-sensitive / temperature-sensitive paint technology; S3, extracting a three-dimensional contour of the model surface to obtain three-dimensional and two-dimensional point clouds; S4, estimating an initial value of a projection matrix; S5, obtaining a two-dimensional re-projection contour point cloud and calculating an average re-projection error; S6, if the average re-projection error is not greater than a threshold value, directly taking the result of S4 as an optimal projection matrix, executing S7, otherwise calculating a new projection matrix, then circulating S5 and S6 until the average re-projection error is not greater than the threshold value, and executing S7; S7, projecting the three-dimensional point cloud onto the pressure / temperature cloud chart according to the projection matrix, extracting pressure and temperature information, and completing three-dimensional pressure / temperature field reconstruction. Compared with the prior art, the application has the advantages of high reconstruction precision and strong robustness.

An electronic device and a control method thereof are provided. The electronic device includes a communication interface, memory storing one or more computer programs, and one or more processors communicatively coupled to the communication interface and the memory. The one or more computer programs include computer-executable instructions that, when executed by the one or more processors, cause the electronic device to obtain a 2-dimensional (2D) map of an indoor space generated based on sensing data, and traveling data obtained by at least one external device, simplify the obtained 2D map, based on the traveling data, and generate a 3-dimensional (3D) map, based on the simplified 2D map.

One embodiment of the present invention sets forth a technique for performing landmark detection. The technique includes generating, via execution of a first machine learning model, a first set of morphable model coefficients associated with a first object depicted in a first image. The technique also includes determining one or more three-dimensional (3D) landmarks on the first object based on the first set of morphable model coefficients and projecting the first set of 3D landmarks onto the first image to generate one or more two-dimensional (2D) landmarks. The technique further includes training the first machine learning model based on one or more losses associated with the one or more 2D landmarks to generate a first trained machine learning model.

A computer-implemented method of performing a quality assurance (QA) analysis for a QA sample may include capturing image sensor data of a QA sample with an image sensor assembly; generating, with a computing device, at least one of a 2D model and a 3D model of the QA sample using the image sensor data; and performing, with a computing device, a QA analysis of the QA sample by comparing data points of the at least one of the 2D model and 3D model of the QA sample and a corresponding 2D model and 3D model from a QA specification of the QA sample.

The application belongs to the field of medical image processing, and relates to a medical image lesion segmentation and three-dimensional reconstruction method and system based on artificial intelligence, aiming to solve the problem of low model precision caused by mutual isolation of segmentation and reconstruction and one-way error transmission. The method comprises the following steps: fusing multi-modal medical images; generating a preliminary lesion mask using a segmentation network; constructing an initial three-dimensional geometric surface based on the mask and performing physically driven surface optimization; projecting the optimized model to the feature space of the segmentation network in reverse, calculating the spatial inconsistency thereof with the network prediction, and generating an attention weight map; feeding the attention weight map back to the segmentation network, iteratively updating the network parameters to refine the segmentation boundary; and based on the final segmentation result after convergence, performing three-dimensional reconstruction guided by network features again. The application constructs a closed-loop feedback and collaborative optimization mechanism between segmentation and reconstruction, significantly improving the accuracy of lesion segmentation and the geometric fidelity of the three-dimensional reconstruction model.

The present application relates to the technical field of new energy training, and particularly relates to a new energy intelligent training and examination system and method based on cloud rendering, which comprises a cloud rendering hub platform system that generates a computing resource allocation scheme according to virtualized and integrated graph computing resources based on course learning request data uploaded by a student terminal device and a student access terminal type; a post skill training and examination module that generates personalized learning evaluation data containing ability short board positioning according to course interaction data and student learning behavior data of the student in a virtual simulation environment; and a virtual-real fusion module that generates force feedback operation data that is synchronously updated with a real job training scene by fusing the virtual training environment and the real job training scene through a data coupling engine. The present application realizes a new energy intelligent training and examination system that seamlessly fuses virtual and real job scenes, and improves the utilization efficiency and precise allocation of cloud rendering platform resources.

This invention provides a method and system for constructing a reliable evaluation dataset for power vision models, belonging to the field of intelligent recognition technology for power vision models. The construction method includes: acquiring collected on-site images and obstacle images; constructing virtual 3D models of power equipment and virtual obstacle models; marking the virtual 3D models and virtual obstacle models to obtain corresponding labels; acquiring multiple images from a virtual perspective on the composite model of the virtual 3D models and virtual obstacle models; determining the positional relationship between the virtual 3D models and virtual obstacles in the images based on the images; and generating a composite image and corresponding composite labels based on the positional relationship, the on-site images, and the obstacle images to form a dataset.

This application discloses an image generation method, apparatus, and system, and a computer-readable storage medium, and belongs to the field of image processing technologies. A terminal or a central control platform first obtains a human body portrait and human body description information of the human body portrait, and obtains a target background template and target template information of the target background template. The human body description information includes human body posture information, the target background template includes a preset position matching the human body portrait, and the target template information includes human body posture information associated with the preset position. Then the terminal or the central control platform places, based on the human body description information and the target template information, the human body portrait at a preset position that is in the target background template and that matches the human body portrait, to obtain a synthesized image.

The disclosure relates to a method (s100) for manufacturing of a casing (1) for thermal control of a component (2) enclosed or substantially enclosed by the casing (1 ). The casing (1 ) is configured to be arranged in a compartment (9). The casing comprises an inner wall (3); an outer wall (5); a cavity (6) arranged between the inner wall (3) and the outer wall (5); and an internal support structure (4) at least partly arranged in the cavity (6). The disclosure further relates to a casing (1 ) for thermal control of a component (2) enclosed or substantially enclosed by the casing (1).

The present disclosure relates to a computer-implemented method and an intraoral scanning system. The computer-implemented method is configured for applying artificial interproximal tooth data to a plurality of dental objects being scanned by an intraoral scanner. The method comprising receiving intraoral scan data of a plurality of dental objects produced by an intraoral scanner, determining a 3D model of the plurality of dental objects based on the intraoral scan data, and wherein the 3D model includes a plurality of teeth vertices, segmenting, based on a tooth segmentation algorithm, the plurality of teeth vertices into a first tooth and a second tooth, and wherein an interproximal surface of the first and second tooth does not include any of the plurality of teeth vertices, fitting, based on a real-tooth fitting algorithm, a first and a second tooth model to the first and the second tooth, respectively, wherein the first and second tooth models include a plurality of reference vertices, generating artificial interproximal vertices by determining which of the plurality of reference vertices overlaps the interproximal surfaces of the first and second tooth, and applying the artificial interproximal vertices to the interproximal surface of the first and second tooth.

A system includes a hardware processor and a memory storing software code. The hardware processor executes the software code to receive a three-dimensional (3-D) image including a plurality of pixels each having a plurality of bins with respective depth values, select, for a first bin of the plurality of bins of a first pixel, a second bin in each of one or more nearest neighbor pixels of the first pixel, the second bin in each of the one or more nearest neighbor pixels having a most similar depth value to a depth value of the first bin. The hardware processor further executes the software code to generate a first depth-aware bin group including the first bin and the second bin in each of the one or more nearest neighbor pixels, and process, using the first depth-aware bin group, the 3-D image to produce a corresponding 3-D output image.

This application provides a three-dimensional construction network training method and apparatus, and a three-dimensional model generation method and apparatus in the field of computer vision, to perform joint training based on a plurality of frames of images and radar point cloud data to obtain a three-dimensional construction network. More accurate depths included in the radar point cloud data may be used as deep supervision. In this way, the three-dimensional construction network can output a more accurate three-dimensional model. The method includes: obtaining the plurality of frames of images and a photographing parameter used by a camera device when the plurality of frames of images are photographed, where the plurality of frames of images include images photographed from a plurality of views; obtaining the radar point cloud data including photographing scenario data; and obtaining the three-dimensional construction network based on the plurality of frames of images, the photographing parameter, and the radar point cloud data. The radar point cloud data is used as deep supervision during three-dimensional construction of the three-dimensional construction network. In this way, depths of the three-dimensional model output by the three-dimensional construction network can be constrained to be closer to depths corresponding to an actual application scenario.

The present invention provides an image processing device that efficiently generates multiple parallel cross-sectional images of a three-dimensional shape model. [Solution] The image processing method of the present disclosure is an image processing method for generating a plurality of parallel cross-sectional images from a three-dimensional shape model, characterized by comprising: an acquisition step of acquiring a plurality of values ​​indicating the distance from a predetermined plane to each part of the three-dimensional shape model; a determination step of determining the distance from the predetermined plane based on the plurality of values; and an image generation step of generating the cross-sectional image at the determined distance.

This disclosure provides a spatial information prediction method, apparatus, computer-readable storage medium, and electronic device. The method includes: acquiring spatial information to be updated for a target object in a current image captured by a target camera on a mobile device; determining three-dimensional predicted coordinates of the target object in the current image based on the spatial information to be updated; transforming the three-dimensional predicted coordinates of the target object to the image coordinate system of the current image to obtain two-dimensional predicted coordinates of the target object; determining a first two-dimensional detection coordinate of the target object in the current image; determining the error between the first two-dimensional detection coordinates and the two-dimensional predicted coordinates; and determining the predicted spatial information of the target object in the current image based on the error and the spatial information to be updated. This disclosure can significantly improve the accuracy of spatial information prediction based on camera-captured images, while effectively reducing costs compared to devices such as LiDAR.

A feature referred to as “opacity micro-maps” provides an efficient representation of geometric detail for ray tracing primitives. One issue with opacity micro-maps is that in a highly parallel system with many rays referencing nearby opacity micro-map data in parallel, a great deal of unnecessary memory traffic may be generated. To combat this unnecessary memory traffic, a mechanism is provided herein for reducing the number of redundant memory requests. According to this mechanism, opacity micro-map circuitry maintains an indication of pending memory requests for opacity micro-map data. If a new request for opacity micro-map evaluation occurs and the data required for that new request is at the same address as the pending memory request, then no additional memory request is generated for the new request. When the data from the pending memory request is returned from memory, that data is used to satisfy all evaluation requests that are outstanding.

The application provides an SBA-based underwater object detection and imaging method and system, wherein the method comprises the following steps: acquiring original sonar data of an underwater array element; constructing an underwater multi-array element model based on the original sonar data and performing filtering and denoising; constructing an underwater beam signal model through signal minimum variance beamforming and acoustic wave beamforming signal processing; optimizing the beam signal model, wherein the optimization comprises signal beamforming convolutional neural network model optimization and underwater acoustic wave particle filtering operation mask optimization, so as to obtain an optimized underwater sonar signal; constructing a two-dimensional image of an underwater object based on the optimized underwater sonar signal by using an SBA algorithm; and generating a three-dimensional image of the underwater object according to the two-dimensional image. The application realizes the improvement of the detection capability and efficiency of the ocean underwater sonar by constructing an acoustic wave beam mathematical model and function operation through innovation on the basis of the beam signal of the acoustic wave emitted and fed back by the ocean sonar equipment.